Now showing items 1-2 of 2
Methods for Improving Generalization and Convergence in Artificial Neural Classifiers
Artificial neural networks have proven to be quite powerful for solving nonlinear classification problems. However, the complex error surfaces encountered in such problems often contain local minima in which gradient based ...
Novel Approaches to Creating Robust Globally Convergent Algorithms for Numerical Optimization
Two optimization algorithms are presented, each of which seeks to effectively combine the desirable characteristics of gradient descent and evolutionary computation into a single robust algorithm. The first method, termed ...